Automatic Generation of Timelines for Past-Web Events

Campos, Ricardo; Pasquali, Arian; Jatowt, Adam; Mangaravite, Vítor; Jorge, Alípio Mário

doi:10.1007/978-3-030-63291-5_18

Cited by 5 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The median year is 1855.0 whereas the mean is 1818.7. Moreover, the authors additionally provide several sentences about the given event, which they call contextual information (CI) 12 . The contextual information are the relevant sentences extracted from Wikipedia, using a series of carefully designed filtering steps, like key entities extraction, sentence filtering, etc.…”

Section: Downstream Tasksmentioning

confidence: 99%

“…For example, researches have been made for addressing time sensitive queries in information retrieval [10,22] leading to the formation of a subset of Information Retrieval area called Temporal Information Retrieval in which both query and document temporal aspects are of key concern. Event detection and ordering [14,41], timeline summarization [3,12,32,40,45], event occurrence time prediction [50], temporal clustering and information retrieval [2,10,11], question answering [34,48] and named entity recognition [1,36] are other example tasks where using time embedded in text proved beneficial.…”

Section: Introductionmentioning

confidence: 99%

“…https://en.wikipedia.org/wiki/Wikipedia:On_this_day/Today, accessed 02/2022 12. For example, the contexual information of the WOTD example in Table1is "The Loyalists never controlled territory unless the British Army occupied it.…”

mentioning

confidence: 99%

See 2 more Smart Citations

TimeBERT: Extending Pre-Trained Language Representations with Temporal Information

Wang¹,

Jatowt²,

Yoshikawa³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Time is an important aspect of text documents, which has been widely exploited in natural language processing and has strong influence, for example, in temporal information retrieval, where the temporal information of queries or documents need to be identified for relevance estimation. Event-related tasks like event ordering, which aims to order events by their occurrence time, also need to determine the temporal information of events. In this work, we investigate methods for incorporating temporal information during pre-training, to further improve the performance on time-related tasks. Compared with BERT which utilizes synchronic document collections (BooksCorpus and English Wikipedia) as the training corpora, we use long-span temporal news collection for building word representations, since temporal information constitutes one of the most significant features of news articles. We then introduce TimeBERT, a novel language representation model trained on a temporal collection of news articles via two new pre-training tasks, which harness two distinct temporal signals to construct timeaware language representation. The experimental results show that TimeBERT consistently outperforms BERT and other existing pretrained models, with substantial gains on different downstream NLP tasks or applications for which time is of importance 1 . CCS CONCEPTS• Information systems → Content analysis and feature selection.

show abstract

Section: Downstream Tasksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TimeBERT: Extending Pre-Trained Language Representations with Temporal Information

Wang¹,

Jatowt²,

Yoshikawa³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Public News Archive: A Searchable Sub-archive to Portuguese Past News Articles

Campos

Correia

Jatowt

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Contrastive text summarization: a survey

Ströhle

Campos

Jatowt

2023

Int J Data Sci Anal

View full text Add to dashboard Cite

In our data-flooded age, an enormous amount of redundant, but also disparate textual data is collected on a daily basis on a wide variety of topics. Much of this information refers to documents related to the same theme, that is, different versions of the same document, or different documents discussing the same topic. Being aware of such differences turns out to be an important aspect for those who want to perform a comparative task. However, as documents increase in size and volume, keeping up-to-date, detecting, and summarizing relevant changes between different documents or versions of it becomes unfeasible. This motivates the rise of the contrastive or comparative summarization task, which attempts to summarize the text of different documents related to the same topic in a way that highlights the relevant differences between them. Our research aims to provide a systematic literature review on contrastive or comparative summarization, highlighting the different methods, data sets, metrics, and applications. Overall, we found that contrastive summarization is most commonly used in controversial news articles, controversial opinions or sentiments on a topic, and reviews of a product. Despite the great interest in the topic, we note that standard data sets, as well as a competitive task dedicated to this topic, are yet to come to be proposed, eventually impeding the emergence of new methods. Moreover, the great breakthrough of using deep learning-based language models for abstract summaries in contrastive summarization is still missing.

show abstract

Automatic Generation of Timelines for Past-Web Events

Cited by 5 publications

References 16 publications

TimeBERT: Extending Pre-Trained Language Representations with Temporal Information

TimeBERT: Extending Pre-Trained Language Representations with Temporal Information

Public News Archive: A Searchable Sub-archive to Portuguese Past News Articles

Contrastive text summarization: a survey

Contact Info

Product

Resources

About